Scrapfly is a web scraping API that enables developers to extract data from websites efficiently, offering features like JavaScript rendering, anti-bot protection bypass, and proxy rotation.

Use it from your agent

One ClawLink account serves every agent you run. Pick the guide for yours, or connect Scrapfly once and call the same tools from all of them.

Scrapfly for OpenClawInstall, pair, connect, first prompt

Scrapfly for Hermes AgentInstall, pair, connect, first prompt MCPClaude Code, Cursor, any MCP clientCLI login or the remote MCP server

Setup

Connect Scrapfly through ClawLink's hosted setup.

Auth: Paste one API key. The credential stays on the ClawLink server; your agent holds only a ClawLink key you can revoke.
Where: the ClawLink dashboard, or ask your agent to connect it.

What your agent can do

Scrapfly exposes 12 tools through ClawLink.

Tool	What it does	Kind
`scrapfly_capture_screenshot`	Capture a full-page or viewport screenshot of a website	Read
`scrapfly_capture_screenshot_head`	Capture screenshot metadata without downloading the image body	Read
`scrapfly_extract_data`	Extract structured data from HTML or other content using AI models, LLM prompts, or custom	Read
`scrapfly_get_account_info`	Retrieve Scrapfly account information	Read
`scrapfly_get_crawler_artifact`	Download crawler artifact files in WARC or HAR format	Read
`scrapfly_get_crawler_contents`	Retrieve extracted content from crawled pages	Read
`scrapfly_get_crawler_status`	Get the current status of a crawler including progress, pages crawled, and completion state	Read
`scrapfly_get_crawler_urls`	Retrieve the list of discovered and crawled URLs from a crawler	Read
`scrapfly_scrape`	Perform a web scraping request	Read
`scrapfly_scrape_post`	Scrape web pages using POST method to send data in the request body	Read
`scrapfly_scrape_with_put`	Scrape web pages using PUT method with body payload	Read
`scrapfly_create_crawler`	Create a new web crawler to recursively crawl an entire website	Write